autoresearch
Bounded research experiment loop that tries hypotheses, measures benchmark evidence, keeps what works, and records what fails. Use when the user asks to optimize a research metric, run an experiment loop, improve model/retrieval/evaluation performance iteratively, or benchmark a research hypothesis.
Why this score
This repo hosts 10 skills, so its 9,992 stars are split between them (about 999 each) for scoring.
Popularity score: 80/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit e39356b48225, with Cisco's open-source skill-scanner.
None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneautoresearch Companion-Inc/feynman · Skill | 80 | ★ 10.0k | ≈78 always | 16d ago |
| dueling-autoresearch gaasher/Agent-Loop-Skills · Skill Both about autoresearch and metric | 51 | ★ 175 | ≈28 always | 4mo ago |
| autoresearch-goal Yeachan-Heo/oh-my-codex · Skill Both about autoresearch | 85 | ★ 34k | ≈14 always | 16d ago |
| lab:autoresearch oliver-kriska/claude-elixir-phoenix · Skill Both about autoresearch and loop | 65 | ★ 567 | ≈22 always | 19d ago |
| autoresearch-finalize davebcn87/pi-autoresearch · Skill Both about autoresearch and experiment | 83 | ★ 8.2k | ≈48 always | 28d ago |
| autoresearch-ml proyecto26/autoresearch-ai-plugin · Skill Both about autoresearch | 47 | ★ 13 | ≈23 always | 4mo ago |